© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 34137
    Prev
    Next
    INDEX
    Explanations

    3-month, action, won

    np_acts-logits-general · gemini-2.5-flash-lite

    offering other types of stories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    شك
    0.48
     ميل
    0.42
     Wolf
    0.41
    米
    0.41
     Herbert
    0.40
     Fred
    0.40
    الية
    0.40
    的人
    0.39
     كم
    0.39
    讀
    0.39
    POSITIVE LOGITS
     unavailability
    0.52
    ordial
    0.49
     elucidation
    0.49
    akkh
    0.47
     있지만
    0.47
     \%,
    0.47
     оказыва
    0.46
     与
    0.46
     retraction
    0.46
     numbness
    0.46
    Activations Density 0.000%

    No Known Activations